DevQueen/deepfake-server

1---2title: Deepfake Detector API3emoji: 🔍4colorFrom: blue5colorTo: green6sdk: docker7app_port: 78608pinned: false9license: mit10---11 12# Deepfake Detector API13 14FastAPI inference service for the [Enhanced Deepfake Detector](https://github.com/oyingrace/deepfake-detection) (LRCN + ViT, blink-aware temporal modeling).15 16> **GitHub project docs:** see [.github/README.md](.github/README.md)17 18## Endpoints19 20| Method | Path | Description |21|--------|------|-------------|22| `GET` | `/health` | Service status and model load state |23| `POST` | `/predict` | Upload a video (multipart form field `file`) |24 25## Example26 27```bash28curl https://devqueen-deepfake-server.hf.space/health29curl -X POST https://devqueen-deepfake-server.hf.space/predict -F "file=@video.mp4"30```31 32## Runtime variables33 34| Variable | Description |35|----------|-------------|36| `ALLOWED_ORIGINS` | Comma-separated frontend URLs for CORS (e.g. your Vercel app) |37| `DEVICE` | `cpu` (default) |38 39## Deploy notes40 41- Synced from GitHub via `.github/workflows/sync-to-hf-space.yml`42- Full setup guide: [huggingface/README.md](huggingface/README.md)43